Massively multilingual models can process text in several languages relying on a shared set of parameters; however, little is known about the encoding of multilingual information in single network units. In this work, we study how two semantic variables, namely valence and arousal, are processed in the latent dimensions of mBERT and XLM-R across 13 languages. We report a significant cross-lingual overlap in the individual neurons processing affective information, which is more pronounced when considering XLM-R vis-à-vis mBERT. Furthermore, we uncover a positive relationship between cross-lingual alignment and performance, where the languages that rely more heavily on a shared cross-lingual neural substrate achieve higher performance scores in semantic encoding.

Massively multilingual models such as mBERT and XLM-R are increasingly valued in Natural Language Processing research and applications, due to their ability to tackle the uneven distribution of resources available for different languages. The models’ ability to process multiple languages relying on a shared set of parameters raises the question of whether the grammatical knowledge they extracted during pre-training can be considered as a data-driven cross-lingual grammar. The present work studies the inner workings of mBERT and XLM-R in order to test the cross-lingual consistency of the individual neural units that respond to a precise syntactic phenomenon, that is, number agreement, in five languages (English, German, French, Hebrew, Russian). We found that there is a significant overlap in the latent dimensions that encode agreement across the languages we considered. This overlap is larger (a) for long- vis-à-vis short-distance agreement and (b) when considering XLM-R as compared to mBERT, and peaks in the intermediate layers of the network. We further show that a small set of syntax-sensitive neurons can capture agreement violations across languages; however, their contribution is not decisive in agreement processing.